Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43941
    Prev
    Next
    INDEX
    Explanations

    references to God and related religious concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KeyValue
    -0.06
    ajs
    -0.06
    oux
    -0.06
    innacle
    -0.06
    aeper
    -0.06
    ijken
    -0.06
    364
    -0.06
    270
    -0.06
    ulan
    -0.05
    pector
    -0.05
    POSITIVE LOGITS
    ly
    0.12
    given
    0.12
     honoring
    0.11
     given
    0.11
     Given
    0.10
     Center
    0.10
    _given
    0.10
     fearing
    0.10
     ordained
    0.10
    -bre
    0.10
    Activations Density 0.018%

    No Known Activations